Skip to main content

Sonar Deep Research

Exhaustive research with expert-level insights

A powerful research model capable of conducting exhaustive searches across hundreds of sources, synthesizing expert-level insights, and generating detailed reports with comprehensive analysis.

Input Tokens

$2
Per 1M Tokens

Output Tokens

$8
Per 1M Tokens

Citation Tokens

$2
Per 1M Tokens

Search Queries

$5
Per 1K Requests

Reasoning Tokens

$3
Per 1M Tokens

Features

Deep research / Reasoning model

Exhaustive research across hundreds of sources

128K context length

Expert-level subject analysis

Detailed report generation

No training on customer data

Real World Use Cases

Academic research and comprehensive reports

Market analysis and competitive intelligence

Due diligence and investigative research

Sample Response Metadata
Success Response
Token Usage
  • Prompt Tokens: 33
  • Completion Tokens: 11,395
  • Citation Tokens: 19,028
  • Search Queries: 21
  • Reasoning Tokens: 193,947
1

Calculate Input Tokens Cost

33 tokens ÷ 1,000,000 × $2 = $0.000066
2

Calculate Output Tokens Cost

11,395 tokens ÷ 1,000,000 × $8 = $0.09116
3

Calculate Citation Tokens Cost

19,028 tokens ÷ 1,000,000 × $2 = $0.038056
4

Calculate Search Queries Cost

21 queries × $5 ÷ 1,000 = $0.105
5

Calculate Reasoning Tokens Cost

193,947 tokens ÷ 1,000,000 × $3 = $0.581841
6

Calculate Total Cost

$0.000066 + $0.09116 + $0.038056 + $0.105 + $0.581841 = $0.816123
Total cost for this request: $0.816123

Advanced Features

Control the computational effort dedicated to each query with the reasoning_effort parameter. This allows you to balance between speed and thoroughness while managing costs by directly impacting the amount of reasoning tokens consumed.Options:
  • "low": Faster, simpler answers with reduced token usage
  • "medium": Balanced approach (default)
  • "high": Deeper, more thorough responses with increased token usage